Cập nhật mã nguồn và file Colab Cache

train_module.py

@@ -13,6 +13,7 @@ from sklearn.ensemble import RandomForestClassifier
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.svm import SVC
 from xgboost import XGBClassifier
+from lightgbm import LGBMClassifier
 import joblib
 from datetime import datetime
 import json
@@ -961,18 +962,38 @@ def train_model(
                 verbosity=0
             )
         elif model_type == 'random_forest':
-            model = RandomForestClassifier(
-                n_estimators=n_estimators,
-                max_depth=max_depth,
-                random_state=42,
-                n_jobs=-1,  # Use all cores
-                verbose=0
-            )
+            if use_gpu:
+                model = XGBClassifier(
+                    n_estimators=n_estimators,
+                    max_depth=max_depth,
+                    tree_method='hist',
+                    device='cuda:0',
+                    random_state=42,
+                    n_jobs=-1,
+                    verbosity=0
+                )
+            else:
+                model = RandomForestClassifier(
+                    n_estimators=n_estimators,
+                    max_depth=max_depth,
+                    random_state=42,
+                    n_jobs=-1,  # Use all cores
+                    verbose=0
+                )
         elif model_type == 'decision_tree':
             model = DecisionTreeClassifier(
                 max_depth=max_depth,
                 random_state=42
             )
+        elif model_type == 'lightgbm':
+            model = LGBMClassifier(
+                n_estimators=n_estimators if n_estimators else 300,
+                max_depth=max_depth if max_depth else -1,
+                learning_rate=learning_rate,
+                class_weight='balanced',
+                random_state=42,
+                device='gpu' if use_gpu else 'cpu'
+            )
         elif model_type == 'svm':
             model = SVC(
                 kernel='rbf',
@@ -1281,7 +1302,7 @@ def train_model(
         class_names = label_encoder.classes_.tolist()
         
         # Classification report as dict
-        from sklearn.metrics import classification_report, confusion_matrix
+        from sklearn.metrics import classification_report, confusion_matrix, accuracy_score
         cls_report = classification_report(y_test, y_pred, target_names=class_names, output_dict=True, zero_division=0)
         
         # Confusion matrix
@@ -1313,9 +1334,9 @@ def train_model(
             "test_accuracy": float(test_score),
             "model_type": model_type,
             "device": device if model_type == 'xgboost' else 'cpu',
-            "n_estimators": n_estimators if model_type in ['xgboost', 'random_forest', 'cnn', 'swin-unet', 'mobilenet-lraspp'] else None,
+            "n_estimators": n_estimators if model_type in ['xgboost', 'random_forest', 'lightgbm', 'cnn', 'swin-unet', 'mobilenet-lraspp'] else None,
             "max_depth": max_depth if model_type not in ['cnn', 'swin-unet', 'mobilenet-lraspp'] else None,
-            "learning_rate": learning_rate if model_type in ['xgboost', 'swin-unet', 'mobilenet-lraspp'] else None,
+            "learning_rate": learning_rate if model_type in ['xgboost', 'lightgbm', 'swin-unet', 'mobilenet-lraspp'] else None,
             "epochs": min(50, n_estimators // 2) if model_type == 'cnn' else (min(60, n_estimators // 2) if model_type in ['swin-unet', 'mobilenet-lraspp'] else None),
             "n_features": X_train.shape[1],
             "n_classes": len(np.unique(y_train)),